Search

Clustering the trajectories of vehicles moving on road networks is a key data mining technique for understanding human mobility patterns, as well as their interactions with urban environments. The development of efficient and scalable trajectory clustering algorithms, however, still faces challenges because of the computational costs when measuring similarities among a large number of network-constrained trajectories. To address this problem, a novel trajectory clustering framework based on the well-developed Density-Based Spatial Clustering of Applications with Noise (DBSCAN) approach is proposed. This proposed framework accurately quantifies similarities using a trajectory representation of continuous polylines in the space and time dimensions, and does not require trajectory discretization. Further, the proposed framework utilizes the space-time buffering concept to formulate ε -neighborhood queries that directly retrieve the ε -neighbors of trajectories and thus avoids computing a trajectory similarity matrix. State-of-the-art trajectory databases and index structures are incorporated to further improve trajectory clustering performance. A comprehensive case study was carried out using an open dataset of 20,161 trajectories. Results show that the proposed framework efficiently executed trajectory clustering on the large test dataset within 3 min. This was approximately 2,700 times faster than existing DBSCAN algorithms. [ABSTRACT FROM AUTHOR]

The availability of Spatiotemporal Big Data has provided a golden opportunity for time geographical studies that have long been constrained by the lack of individual-level data. However, how to store, manage, and query a huge number of time geographic entities effectively and efficiently with complex spatiotemporal characteristics and relationships poses a significant challenge to contemporary GIS platforms. In this article, a hierarchical compressed linear reference (CLR) model is proposed to transform network-constrained time geographic entities from three-dimensional (3D) (x, y, t) space into two-dimensional (2D) space. Accordingly, time geographic entities can be represented as 2D spatial entities and stored in a classical spatial database. The proposed CLR model supports a hierarchical linear reference system (LRS) including not only underlying a link-based LRS but also multiple higher-level route-based LRSs. In addition, an LRS-based spatiotemporal index structure is developed to index both time geographic entities and the corresponding hierarchical network. The results of computational experiments on large datasets of space–time paths and prisms show that the proposed hierarchical CLR model is effective at storing and managing time geographic entities in road networks. The developed index structure achieves satisfactory query performance in milliseconds on large datasets of time geographic entities. [ABSTRACT FROM AUTHOR]

Short-term traffic prediction is of great importance to the management of traffic congestion, a pervasive and difficult-to-solve problem in many metropolises all over the world. However, existing studies on traffic prediction contain rough traffic information at the carriageway level that ignore the distinction between different turns in one intersection. With the aim of predicting traffic at road intersections from big trace data on a finer scale, this study proposes a novel method, the fine-grained traffic prediction method (FTPG) with a graph attention network (GAT), which predicts traffic information, including traffic flow speeds, traffic states, and average queue lengths, at the turn level. In the FTPG, a method for estimation of the queue starting point is proposed to improve the accuracy of traffic information detection. Furthermore, the topology is constructed under turn-level conditions, and a GAT-based method, the spatio-temporal residual graph attention network (ST-RGAN), is proposed to improve the prediction accuracy. Experiments are performed using taxi GPS trace data collected in the city of Wuhan and show that the proposed FTPG method can make predictions with fine-grained traffic information for road intersections accurately and robustly. [ABSTRACT FROM AUTHOR]

Sampling fraction is crucial to sampling-related studies and applications, especially in the big data era when most data are neither originally designed nor controllable in the data collection process. A common concern among researchers is 'what's the modelling accuracy when using a sample?'. Taking intra-city human mobility as the study objective, this study utilizes a simple and direct method to analyse the influences of various sampling fractions on modelling accuracy. Five common intra-city human mobility indicators (travel distance, travel time, travel frequency, radius of gyration and movement entropy) are evaluated considering mean value, median and probability distribution. Experimental results demonstrate that the representativeness of each considered indicator converges to 1 in its own unique rate and variances. The minimum required sampling fractions to satisfy specific accuracies differ for various indicators and evaluation measures. To further investigate how related factors influence the modelling accuracy of sampling fractions, additional experiments are conducted considering multiple sampling methods, study scopes, and data sources. Several interesting general findings are observed. This study provides a reference for other sampling-based applications. [ABSTRACT FROM AUTHOR]

Highlights • We propose an indexing approach to accelerate access to Earth Observation data. • The distributed indexing structure improves the scalability to support Earth Observation Big Data. • The indexing algorithm considers both spatial and workload balancing by integrating Earth Observation data access patterns. • Fast Earth Observation data access promotes the transformation of Big Data into Big Value. Abstract With the rapid advancement of Earth Observation systems, Earth Observation data has been collected and accumulated at an unprecedented fast rate. Earth Observation Big Data emerged with new opportunities for human to better understand the Earth systems, but also pose a tremendous challenge for efficiently transforming Big Data into Earth Observation Big Value. Targeting on this challenge, a well-organized data index is a key to enhance the “Data-Value” transformation by accelerating the access to data. Although various data indexing approaches have been proposed with different optimization objectives, literature shows that there are still apparent limitations for Earth Observation data indexing. This paper aims to build a spatiotemporal indexing for Earth Observation Big Data. Specifically, a) to support various Earth Observation Data Infrastructures, we adopt an indexing framework to efficiently retrieve data with various textual, spatial and temporal requirements; b) a distributed indexing structure is designed to improve the index scalability; c) data access pattern is integrated to the indexing algorithm for both spatial and workload balancing. The results show that our indexing approach outperforms traditional indexing approaches and accelerates the access to Earth Observation data. We envision that data indexing will become a key technology that drives fundamental Earth Observation advancements in the Big Data era. [ABSTRACT FROM AUTHOR]

Spatiotemporal proximity analysis to determine spatiotemporal proximal paths is a critical step for many movement analysis methods. However, few effective methods have been developed in the literature for spatiotemporal proximity analysis of movement data. Therefore, this study proposes a space-time-integrated approach for spatiotemporal proximal analysis considering space and time dimensions simultaneously. The proposed approach is based on space-time buffering, which is a natural extension of conventional spatial buffering operation to space and time dimensions. Given a space-time path and spatial tolerance, space-time buffering constructs a space-time region by continuously generating spatial buffers for any location along the space-time path. The constructed space-time region can delimit all space-time locations whose spatial distances to the target trajectory are less than a given tolerance. Five space-time overlapping operations based on this space-time buffering are proposed to retrieve all spatiotemporal proximal trajectories to the target space-time path, in terms of different spatiotemporal proximity metrics of space-time paths, such as Fréchet distance and longest common subsequence. The proposed approach is extended to analyze space-time paths constrained in road networks. The compressed linear reference technique is adopted to implement the proposed approach for spatiotemporal proximity analysis in large movement datasets. A case study using real-world movement data verifies that the proposed approach can efficiently retrieve spatiotemporal proximal paths constrained in road networks from a large movement database, and has significant computational advantage over conventional space-time separated approaches. [ABSTRACT FROM AUTHOR]

The size of phytoplankton not only influences its physiology, metabolic rates and marine food web, but also serves as an indicator of phytoplankton functional roles in ecological and biogeochemical processes. Therefore, some algorithms have been developed to infer the synoptic distribution of phytoplankton cell size, denoted as phytoplankton size classes (PSCs), in surface ocean waters, by the means of remotely sensed variables. This study, using the NASA bio-Optical Marine Algorithm Data set (NOMAD) high performance liquid chromatography (HPLC) database, and satellite match-ups, aimed to compare the effectiveness of modeling techniques, including partial least square (PLS), artificial neural networks (ANN), support vector machine (SVM) and random forests (RF), and feature selection techniques, including genetic algorithm (GA), successive projection algorithm (SPA) and recursive feature elimination based on support vector machine (SVM-RFE), for inferring PSCs from remote sensing data. Results showed that: (1) SVM-RFE worked better in selecting sensitive features; (2) RF performed better than PLS, ANN and SVM in calibrating PSCs retrieval models; (3) machine learning techniques produced better performance than the chlorophyll-a based three-component method; (4) sea surface temperature, wind stress, and spectral curvature derived from the remote sensing reflectance at 490, 510, and 555 nm were among the most sensitive features to PSCs; and (5) the combination of SVM-RFE feature selection techniques and random forests regression was recommended for inferring PSCs. This study demonstrated the effectiveness of machine learning techniques in selecting sensitive features and calibrating models for PSCs estimations with remote sensing. [ABSTRACT FROM AUTHOR]

With the development of information and communication technology, spatial-temporal data that contain rich human mobility information are growing rapidly. However, the consistency of multi-mode human travel behind multi-source spatial-temporal data is not clear. To this aim, we utilized a week of taxies' and buses' GPS trajectory data and smart card data in Shenzhen, China to extract city-wide travel information of taxi, bus and metro and tested the correlation of multi-mode travel characteristics. Both the global correlation and local correlation of typical travel indicator were examined. The results show that: (1) Significant differences exist in of urban multi-mode travels. The correlation between bus travels and taxi travels, metro travel and taxi travels are globally low but locally high. (2) There are spatial differences of the correlation relationship between bus, metro and taxi travel. These findings help us understanding urban travels deeply therefore facilitate both the transport policy making and human-space interaction research. [ABSTRACT FROM AUTHOR]

Intersections are the critical parts where different traffic flows converge and change directions, forming “bottlenecks” and “clog points” in urban traffic. Intersection travel time is an important parameter for public route planning, traffic management, and engineering optimization. Based on low-frequency spatial-temporal Global Positioning System (GPS) trace data, this article presents a novel method for estimating intersection travel time. The proposed method first analyzes the different travel patterns of vehicles through an intersection, then determines the range of an intersection dynamically and reasonably, and obtains traffic flow speed and delay at the intersection under different travel patterns using a fuzzy fitting approach. Finally, the average intersection travel time is estimated from traffic flow speed and delay and intersection range in different travel patterns. Wuhan road network data and GPS trace data from taxicabs were tested in the experiments and the results show that the proposed method can improve the accuracy of travel time estimation at city intersections. [ABSTRACT FROM AUTHOR]

There has been a resurgence of interest in time geography studies due to emerging spatiotemporal big data in urban environments. However, the rapid increase in the volume, diversity, and intensity of spatiotemporal data poses a significant challenge with respect to the representation and computation of time geographic entities and relations in road networks. To address this challenge, a spatiotemporal data model is proposed in this article. The proposed spatiotemporal data model is based on a compressed linear reference (CLR) technique to transform network time geographic entities in three-dimensional (3D) (x,y,t) space to two-dimensional (2D) CLR space. Using the proposed spatiotemporal data model, network time geographic entities can be stored and managed in classical spatial databases. Efficient spatial operations and index structures can be directly utilized to implement spatiotemporal operations and queries for network time geographic entities in CLR space. To validate the proposed spatiotemporal data model, a prototype system is developed using existing 2D GIS techniques. A case study is performed using large-scale datasets of space-time paths and prisms. The case study indicates that the proposed spatiotemporal data model is effective and efficient for storing, managing, and querying large-scale datasets of network time geographic entities. [ABSTRACT FROM AUTHOR]

Vehicle electrification is a promising approach towards attaining green transportation. However, the absence of charging stations limits the penetration of electric vehicles. Current approaches for optimizing the locations of charging stations suffer from challenges associated with spatial–temporal dynamic travel demands and the lengthy period required for the charging process. The present article uses the electric taxi (ET) as an example to develop a spatial–temporal demand coverage approach for optimizing the placement of ET charging stations in the space–time context. To this end, public taxi demands with spatial and temporal attributes are extracted from massive taxi GPS data. The cyclical interactions between taxi demands, ETs, and charging stations are modeled with a spatial–temporal path tool. A location model is developed to maximize the level of ET service on the road network and the level of charging service at the stations under spatial and temporal constraints such as the ET range, the charging time, and the capacity of charging stations. The reduced carbon emission generated by used ETs with located charging stations is also evaluated. An experiment conducted in Shenzhen, China demonstrates that the proposed approach not only exhibits good performance in determining ET charging station locations by considering temporal attributes, but also achieves a high quality trade-off between the levels of ET service and charging service. The proposed approach and obtained results help the decision-making of urban ET charging station siting. [ABSTRACT FROM AUTHOR]

Urban traffic pattern reflects how people move and how goods are transported, which is crucial for traffic management and urban planning. With the development of sensing techniques, accumulated sensor data are captured for monitoring vehicles, which also present the opportunities of big transportation data, especially for real-time interactive traffic pattern analysis. We propose a three-layer framework for the recognition and visualization of multiscale traffic patterns. The first layer computes the middle-tier synopses at fine spatial and temporal scales, which are indexed and stored in a geodatabase. The second layer uses synopses to efficiently extract multiscale traffic patterns. The third layer supports real-time interactive visual analytics for intuitive explorations by end users. An experiment in Shenzhen on taxi GPS trajectories that were collected over one month was conducted. Multiple traffic patterns are recognized and visualized in real-time. The results show the satisfactory performance of proposed framework in traffic analysis, which will facilitate traffic management and operation. [ABSTRACT FROM AUTHOR]

Abstract Based on our GEOSS Clearinghouse operating experience, we summarized the three Earth Observation (EO) Big Data access challenges, namely, fast access, accurate service estimation and global access, and two essential research questions: are there any spatiotemporal patterns when end users access EO data, and how can these spatiotemporal patterns be utilized to better facilitate EO Big Data access? To tackle these two research questions, we conducted a two-year pattern analysis with 2+ million user access records. The spatial pattern, temporal pattern and spatiotemporal pattern of user-data interactions were explored. For the second research question, we developed three spatiotemporal optimization strategies to respond to the three access challenges: a) spatiotemporal indexing to accelerate data access, b) spatiotemporal service modeling to improve data access accuracy and c) spatiotemporal cloud computing to enhance global access. This research is a pioneering framework for spatiotemporal optimization of EO Big Data access and valuable for other multidisciplinary geographic data and information research. Highlights • Spatiotemporal patterns of user-data interaction were explored. • Three Earth Observation Big Data access challenges were summarized. • We respond access challenges with a spatiotemporal optimization framework. [ABSTRACT FROM AUTHOR]

• The EV acceptability in ride-hailing drivers is quantified. • Ride-hailing drivers is less favored electric vehicles. • The power load profile generated by ride-hailing EVs has a diurnal pattern. • The payback time for the ride-hailing adoption of BEVs and PHEVs is 4.3–12.8 years. The acceptability, energy consumption, and environmental benefits of electric vehicles are highly dependent on travel patterns. With increasing ride-hailing popularity in mega-cities, urban mobility patterns are greatly changing; therefore, an investigation of the extent to which electric vehicles would satisfy the needs of ride-hailing drivers becomes important to support sustainable urban growth. A first step in this direction is reported here. GPS-trajectories of 144,867 drivers over 104 million km in Beijing were used to quantify the potential acceptability, energy consumption, and costs of ride-hailing electric vehicle fleets. Average daily travel distance and travel time for ride-hailing drivers was determined to be 129.4 km and 5.7 h; these values are substantially larger than those for household drivers (40.0 km and 1.5 h). Assuming slow level-1 (1.8 KW) or moderate level-2 (7.2 KW) charging is available at all home parking locations, battery electric vehicles with 200 km all electric range (BEV200) could be used by up to 47% or 78% of ride-hailing drivers and electrify up to 20% or 55% of total distance driven by the ride-hailing fleet. With level-2 charging available at home, work, and public parking, the acceptance ceiling increases to up to 91% of drivers and 80% of distance. Our study suggests that long range BEVs and widespread level-2 charging infrastructure are needed for large-scale electrification of ride-hailing mobility in Beijing. The marginal benefits of increased all electric range, effects on charging infrastructure distribution, and payback times are also presented and discussed. Given the observed heterogeneity of ride-hailing vehicle travel, our study outlines the importance of individual-level analysis to understand the electrification potential and future benefits of electric vehicles in the era of shared smart transportation. [ABSTRACT FROM AUTHOR]

Abstract Sensing turn-level or lane-level traffic conditions not only enables navigation systems to provide users with more detailed and finer-grained information, it can also improve the accuracy in the search for the fastest routes and in short-term predictions of traffic conditions. The widespread collection and application of taxis' GPS data enable us to sense urban traffic flow on a large scale. Since current GPS positional accuracy cannot reach the lane level, existing approaches using GPS trajectory data only analyze traffic conditions at the road level. Whereas some studies attempted to detect lane-level traffic conditions using lane-level data, the high cost of data collection considerably limits their practical application. To address this limitation, this article proposes an approach for detecting traffic congestion from taxis' GPS trajectories at the turn level. Based on analyzing features of GPS trajectories and identifying valid trajectory segments, the proposed approach detects congested trajectory segments of three different intensities. It then identifies congestion events in each turning direction through a clustering approach. Finally, congestion intensity, time of the day when congestion occurred and queue length in each turning direction at a road intersection in Wuhan, China are explored and analyzed. The results support the feasibility of this approach for detecting and analyzing traffic congestion at the turn level. Compared with other approaches that detect traffic congestion using GPS trajectory data, the proposed approach analyzes congestion at a finer-grained level (the turn level). Compared with other approaches that detect traffic congestion at the lane level, the proposed approach can sense traffic congestion over a larger area and at a lower cost. Highlights • This study proposes an approach to filter taxis' GPS data that reflect the real traffic condition. • The trajectories that reflect real traffic conditions are differentiated based on machine-learning technique. • This study proposes an approach that can detect turn-level congestions in multiple dimensions. • It is a fine-grained congestion analysis approach using taxi GPS data, which can be applied to other study areas. • Compared with other approaches, it analyzes congestions at a finer-grained level, over a larger area and at a lower cost. [ABSTRACT FROM AUTHOR]

Abstract Traffic-related fuel consumption and emissions pose a severe problem with adverse impact on human health and urban sustainability. GPS trajectory data can provide useful insights into the quantities and distributions of fuel consumption and emissions. Previous research has primarily focused on understanding the spatiotemporal distributions of fuel consumption and emissions with GPS trajectory data, but has not paid adequate attention to estimation accuracy. Thus, this study proposes a method that estimates vehicular fuel consumption and emissions at a fine-grained level based on analysis of vehicles' mobile activities, stationary activities with engine-on, and stationary activities with engine-off. Using the analytical framework of space-time paths in time geography, this study first builds space-time paths of individual vehicles, extracts moving parameters and analyzes the activities from each space-time path segment (STPS). Based on the activity analysis, we then estimate fuel consumption and emissions using a microscopic model (CMEM), and distinguish between the cold-start phases and the hot phases in the space-time paths. In the case study, the fuel consumption and emissions for individual trajectories and a road network were estimated and analyzed. The distribution of activity-related fuel consumption was also explored. The effectiveness of the proposed methodology is illustrated using three datasets that were collected from vehicles with various types of engines, with estimation accuracy of over 90%. Highlights • Using space-time paths in time geography, individual vehicle activities are analyzed by mobile and stationary activities. • Cold- and hot-start phases are distinguished in space-time paths, before emission estimation using CMEM based on activity. • The fuel consumption and emissions for individual trajectories and a road network were estimated and analyzed. • The distribution of activity-related fuel consumption was also explored. [ABSTRACT FROM AUTHOR]

Understanding urban public ridership is essential for promoting public transportation. However, limited efforts have been made to reveal the spatial variations of multi-modal public ridership (such as buses, metro systems, and taxis) and the underlying controlling factors. This study explores multi-modal public ridership and compares the similarities and differences of the associated factors. Daily bus, metro, and taxi ridership patterns are first extracted from multiple sources of big transportation data, including vehicle (bus and taxi) GPS trajectories and smart card data. Multivariate regression analysis and geographically weighted regression analysis are used to reveal the associations between these data and demographic, land use, and transportation factors. An empirical study in Shenzhen, China, suggests that employment, mixed land use, and road density have significant effects on the ridership of each mode; however, some effects vary from negative to positive across the city. The results also indicate that road density, income, and metro accessibility do not have significant effects on metro, transit or bus ridership. These findings suggest that the effects of the associated factors vary depending on the mode of travel being considered and that the city should carefully consider which factors to emphasize in formulating future transport policy. [ABSTRACT FROM AUTHOR]

Lane-based road information plays a critical role in transportation systems, a lane-based intersection map is the most important component in a detailed road map of the transportation infrastructure. Researchers have developed various algorithms to detect the spatial layout of intersections based on sensor data such as high-definition images/videos, laser point cloud data, and GPS traces, which can recognize intersections and road segments; however, most approaches do not automatically generate Lane-based Intersection Maps (LIMs). The objective of our study is to generate LIMs automatically from crowdsourced big trace data using a multi-hierarchy feature extraction strategy. The LIM automatic generation method proposed in this paper consists of the initial recognition of road intersections, intersection layout detection, and lane-based intersection map-generation. The initial recognition process identifies intersection and non-intersection areas using spatial clustering algorithms based on the similarity of angle and distance. The intersection layout is composed of exit and entry points, obtained by combining trajectory integration algorithms and turn rules at road intersections. The LIM generation step is finally derived from the intersection layout detection results and lane-based road information, based on geometric matching algorithms. The effectiveness of our proposed LIM generation method is demonstrated using crowdsourced vehicle traces. Additional comparisons and analysis are also conducted to confirm recognition results. Experiments show that the proposed method saves time and facilitates LIM refinement from crowdsourced traces more efficiently than methods based on other types of sensor data. [ABSTRACT FROM AUTHOR]

The debates about patients' decisions regarding which hospital to visit have been shown in many health research literature for the past few years. Researchers have developed various methods to understand hospital bypass behaviour of patients; however, previous studies ignore the impact of spatial heterogeneity and awareness of patients about surrounding hospitals such as travel distance and hospital distributions in the process of bypass behaviour definitions and evaluations. To address these limitations, this study puts forward a Hospital Bypass Index (HBI) to understand urban hospital bypass behaviour by using big trace data collected by urban taxis. To evaluate the bypass behaviour, we defines three evaluation indicators for HBI including a potential bypass rate, an overall distance decay parameter, and a diurnal variation in distance decay parameter by mining large-scale patient-hospital trips from a spatiotemporal perspective. Experiments are conducted with 30 general hospitals and 13 specialty hospitals in Wuhan city, China, by using one month of taxi traces. The results of bypass behaviour evaluation and comparisons indicate that the proposed method is effective and feasible, which is promising for health departments to optimize the medical services and rationally allocate the medical facilities. • This study introduces a new method to understand urban hospital bypass behaviour based on taxi trace data; • The new method addresses the absence of spatial heterogeneity and patient awareness in previous studies; • The results indicate that the diurnal variation in distance decay parameter can improve the accuracy of bypass analysis; • Taking Wuhan, China as an example, this study analyses the urban hospital bypass phenomenon with real taxi traces. [ABSTRACT FROM AUTHOR]

• Three alternative urban datasets are presented to portray urban vibrancy. • A comparative empirical study is conducted to examine multisource urban big data. • The results demonstrate the commonalities and differences in urban vibrancy proxies. Understanding urban vibrancy aids policy-making to foster urban space and therefore has long been a goal of urban studies. Recently, the emerging urban big data and urban analytic methods have enabled us to portray citywide vibrancy. From the social sensing perspective, this study presents a comprehensive and comparative framework to cross-validate urban vibrancy and uncover associated spatial effects. Spatial patterns of urban vibrancy indicated by multisource urban sensing data (points-of-interest, social media check-ins, and mobile phone records) were investigated. A comprehensive urban vibrancy metric was formed by adaptively weighting these metrics. The association between urban vibrancy and demographic, economic, and built environmental factors was revealed with global regression models and local regression models. An empirical experiment was conducted in Shenzhen. The results demonstrate that four urban vibrancy metrics are all higher in the special economic zone (SEZ) and lower in non-SEZs but with different degrees of spatial aggregation. The influences of employment and road density on all vibrancy metrics are significant and positive. However, the effects of metro stations, land use mix, building footprints, and distance to district center depend on the vibrancy indicator and location. These findings unravel the commonalities and differences in urban vibrancy metrics derived from multisource urban big data and the hidden spatial dynamics of the influences of associated factors. They further suggest that urban policies should be proposed to foster vibrancy in Shenzhen therefore benefit social wellbeing and urban development in the long term. They also provide valuable insights into the reliability of urban big data-driven urban studies. [ABSTRACT FROM AUTHOR]